Bring Ml Observability
to OpenAI Agents SDK

Connect your Arize AI account to any AI agent and take full control of your machine learning observability and automated model monitoring workflows through natural conversation.

What you can do

• Project & Trace Orchestration — List and monitor active ML tracing projects programmatically, retrieving detailed high-fidelity execution spans and telemetry data in real-time
• Dataset Lifecycle Management — Programmatically create and manage datasets for model evaluation and validation to maintain a perfectly coordinated ML infrastructure
• Experiment Monitoring — Access and track ML experiments to understand high-fidelity model performance, drift, and data quality across different environments
• Model Intelligence Discovery — Retrieve detailed metadata for specific ML models to coordinate your organizational AI strategy directly through your agent
• Operational Monitoring — Access account-level settings and verify API connectivity directly through your agent for instant performance reporting

How it works

1. Subscribe to this server
2. Retrieve your API Key from your Arize dashboard (Settings > API)
3. Start orchestrating your ML observability pipeline from Claude, Cursor, or any MCP client

No more manual logging into observability portals to check model drift or trace spans. Your AI acts as your dedicated ML engineer and observability coordinator.

Who is this for?

• ML Engineers — instantly retrieve span details and analyze model traces using natural language commands
• Data Scientists — monitor experiment results and manage datasets for validation without leaving your creative workspace
• AI Developers — automate the oversight of LLM and ML model health through simple AI queries